3e8e7e8e6d
update model_replay route ( #34774 )
...
* update route
* Update selfdrive/test/process_replay/model_replay.py
Co-authored-by: Maxime Desroches <desroches.maxime@gmail.com>
---------
Co-authored-by: Maxime Desroches <desroches.maxime@gmail.com>
2 months ago
c82af71e83
model_replay: raise max `modelV2` exec time ( #34505 )
...
raise
3 months ago
2eb3585dae
Not Too Shabby Model ( #34484 )
...
* b25c27a8-263b-4f3f-b1f8-72ac49b4f9c7/700
* replay
* model_replay: support empty
3 months ago
52f935da74
model_replay: check `modelExecutionTime` ( #34457 )
...
* metric
* fix
* format
* table
* test failure
* cleanup
* 3
* 4
3 months ago
c8264cbf2c
Notre Dame model in tinygrad ( #34324 )
...
* release model: 6f23a03f-486b-4d3e-a314-19d149644c7c/700
* old style model in tinygrad
* fix desire
* tg hack
* 20Hz
* no gas probs
* No gas here
* better indexing
---------
Co-authored-by: Yassine Yousfi <yyousfi1@binghamton.edu>
4 months ago
847a5ce1f3
ci: faster model_replay ( #34036 )
...
* cache draft
* fix
* fix
* fix
* better
* zst
* more
* try
* pool
* fix
* fix
* revert :C
* better
* cleanup
* no cache
* this too
5 months ago
360bb68547
proposed should be orange
5 months ago
a4848ceee9
Add driverStateV2 plots to model replay ( #33967 )
6 months ago
e6afe355d4
model_replay: save plots for each commits ( #33886 )
...
* fix
* better
* cleanup
6 months ago
a8908b5c08
model_replay: skip report if no PR associated with the branch ( #33866 )
...
* no pr number
* better
* test
* cleanup
6 months ago
f11e5492f8
ci: keep old comment on model replay report ( #33759 )
...
keep old
7 months ago
596d8b13bb
ci: model_replay improvements ( #33753 )
...
* diff
* tr
* cleanup
* at the end
* fix
7 months ago
2e83e37984
jenkins: model replay report in PR ( #33723 )
...
* first
* first
* first
* token
* edit previous comment
* clean
* plots
* linter
* cleaner
* comment
* save ref
* fix
* remove refs
* add tokens
* fix branch
* table
* fix
* real data
* title
* github
* fix
* github api
* better
* clean
* errors
* create bucket
* true
* fix
7 months ago
3b08501db3
Game Boy Model V3 ( #33674 )
...
* f4afab38-2ee3-4a71-904a-f2e5d4ec119a/400
* Model replay
* fix onnx cast
* tol
7 months ago
04a266eaeb
Game Boy Model ( #33661 )
...
* 559069cd-40a6-4456-9052-08659f376ca3/370
* 028fb9bc-b33e-4c26-9cf7-e3c44a85276a/400
* Update ref
* Update tolerance
7 months ago
876f192112
exec DM model with gpu ( #33609 )
...
* half
old-commit-hash: 9f72eca003d4637ca7fe847ebaf925c694fc2e84
* optimed
old-commit-hash: 6e36e2a12e09275ec21d1590012a92b05ca52ff5
* thneed
old-commit-hash: 419a06c09c0c767d828bcd1e118bc575898c343a
* exec
old-commit-hash: 0059c27ec11b076a37f65d604ed135ea6541b1a6
* runner
old-commit-hash: 34232ada94450ce541eaef546197fa219810a891
* runs but
old-commit-hash: 3db37c00b6a64908293b4de8d8b56e80308cd8f2
* it is 01
old-commit-hash: a160d81eb1a7e77abbef959b44f602610f68f665
* np
old-commit-hash: c1caff6ba648cc2c0094c71b2ea074f01c3c2dc8
* module url
old-commit-hash: 6f4902c4d384263a53e2c1d14d93b5ff864b6a5f
* new
old-commit-hash: 779ae79b1bc3df6374fb6663ac8592e107a6e504
* ds fast
* is this work
* corcention
* real timing
* no reg
* interim gather
* 0e4a9c7b
* fa69be01, and halve
* list
* cleanup
* slighly faster
* setprotlt
* expected
* replay ref
* more powar
* reluctantly
* bump tg
* 8
* less
* less
* bump tg
* better than exp
* closer
* cc
* see diff
* commits
* was right
* to 32 cast
* remove dlc file
* support both
* dspExecutionTime -> gpuExecutionTime
* ignore
* time ref
* ref commit
* last
---------
Co-authored-by: Comma Device <device@comma.ai>
7 months ago
ba7039785c
More reasonable model replay tolerance ( #33652 )
7 months ago
48938098e0
Add modelExecutionTime to DrivingModelData ( #33606 )
...
* Add model execution time to DrivingModelData
* Update model replay ref commit
* Update ref commit again
* Ignore this field in model replay
* Back to original ref commit
* Bring back
---------
Co-authored-by: Comma Device <device@comma.ai>
7 months ago
786aff27da
azure_container: pass the filename explicitely when using get_url ( #33407 )
...
* Pass filename explicitely when using azure container
* Do not update segments in test_processes
* openpilotci_source_zst
* Fix static analysisc
old-commit-hash: b5958ebb60
8 months ago
539c828861
tools: keep re pattern file small ( #33084 )
...
remove bz2 from re file
old-commit-hash: e68bb26e14
9 months ago
02a35949dc
drivingModelData: frameDropPerc ( #32871 )
...
* Smokes! lets go!
* Ignore it in model replay
old-commit-hash: 417f1e2139
10 months ago
102188c245
drivingModelData: new model packet for qlogs ( #32821 )
...
* Mini model v2 prototype
* Apply suggestions
* Add meta
* Support for new packet in model
* Support in process replay
* Meta
* Add it to services
* Update model replay
* Add drivingModelData in model_replay
* Update ref
* MAX_FRAMES*3
* No modelv2, but drivingModelData at 2hz
* Polypath
* Dont use keyword
* Update model ref commit
* xyz coeff
* Fix field name
* Update ref commit
* Min qlog size 0.6
---------
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: 2059f986df
10 months ago
6745358478
remove mapbox references ( #32811 )
...
old-commit-hash: bccccde568
10 months ago
75a69e12b3
disable navigate on openpilot ( #32106 )
...
* 2eedcd90-b7db-46cb-86be-740f48ded7ab/700
* noop ciao
* here too
* mapsd too
* update translations
* disable mapsd test from test onroad
* disable mapRenderState test from timings
* lint
* fix exp mode toggle panel
* update tr
* french done
* dont build mapd
* only no nav
* just comment
* deprecate nav fields
* rm not comment
* dont deprecate too much
* remove from services
* merge cereal
old-commit-hash: 754dd45ffa
1 year ago
a5bc36ea9d
move git commands to common/git.py ( #31921 )
...
move git into common/git.py
old-commit-hash: 4fbc8a3896
1 year ago
f60cbbb04b
modeld: prep for camera transform refactor ( #31820 )
...
* modeld: prep for camera transform refactor
* update refs
* add pub
* do setup
old-commit-hash: 7436aa8b05
1 year ago
66dbadb029
Delete lat planner ( #31089 )
...
* Initial commit
* Fixup
* typo
* ignore lateral plan
* Update cereal
* Remove lateralPlan
* Fix release build
* Fix release build
* give car params
* Add carParams to include_all_types
* Write car param in powerdraw test
* add demo mode
* Update model regf
* proc replay ref commit
* Try
* Move enum definition
* Update cereal
* typo
* Write car param for modeld test
* Update ref
* Update model ref again
---------
Co-authored-by: Kacper Rączy <gfw.kra@gmail.com>
old-commit-hash: e6c97c3846
1 year ago
4b7edec2b0
LogReader: move opci to tools/lib ( #31021 )
...
move opci
old-commit-hash: 7d400112df
1 year ago
e525f47141
model_replay: allow skipping modeld/dmodeld ( #30365 )
...
* skip model
* sa
---------
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: c52f2ec19b
2 years ago
f2dcaf6f79
compare_logs: better names for short/long diffs ( #30263 )
...
* better names
* dont need that
* those too
old-commit-hash: def2b93895
2 years ago
338987a5d2
scripts: format diff when comparing logs ( #30174 )
...
* move format diff to compare_logs to pretty print
* smaller
old-commit-hash: a1ca5dc484
2 years ago
7a0a5c604e
model replay: add cameraOdometry ( #30007 )
...
* model replay: add back cameraOdometry coverage
* update refs
* try again
* fix cmp log
old-commit-hash: 5f318faf93
2 years ago
16ec56398c
add openpilot prefix to imports ( #29498 )
...
* add openpilot prefix to imports
* more
* more
* fix docs
* fix linter
* bump submodules
* fix patched tests
* update dynamic imports
* debug
* Revert "debug"
This reverts commit db5e13b991a9626f95b6
2 years ago
0a6b589f23
dmonitoringmodeld: initialize model first ( #29080 )
...
* hacky fix
* even better
* ordering
* clean up
* fix model replay
* add comment
* catch sigint
old-commit-hash: 12ed894362
2 years ago
1fa42d0b97
process_replay: modeld and dmonitoringmodeld support ( #28463 )
...
* vipc support. modeld and dmonitoringmodeld configs
* Update cereal
* Add vision meta
* Use vision meta in process replay
* Exclude modeld and dmonitoringmodeld from test_processes
* Refactor other pieces of code to use vision meta
* remove unnecessary imports
* Add MAX_FRAMES_PER_SEGMENT
* cameraState migration
* Move camera state migration to migration module
* model_replay refactor
* Fix lint issues
* Reduce number of vipc buffers to 2
* Update spinner message
* Update model replay ref
* Support the new log order
* Replace CameraFrameSizes with dict. Add encode_index field
* Migrate camera states based on encode indices
* Refactor process replay
* Refactor model replay
* Remove unnecessary print
* Update model replay ref
* Make camera state migration optional
* Remove unused import
* Add ignore_alive_pubs field
* Add assertion for carParams inside fingerprinting callback
* Remove WideCameraOnly param setup
* Refactor ModeldCameraSyncRcvCallback
* Update model replay ref commit
* Fix camera state migration
* Only migrate camera states when process has vision pubs
* Refactor model replay again
* Fix linter issues
* One more linter fix
* Update model replay ref commit
old-commit-hash: 2c617e0c7a
2 years ago
2edd65ad4e
process_replay: helpers ( #28367 )
...
* process_replay helper
* Refactor
* refactor check_enabled uses
* fix __init__
* noqa in __init__ imports
* Move compare_logs outside of process_replay
* Move save_logs to tools.lib.helpers
* Remove save_log from compare_logs
* fix lint issues
old-commit-hash: 64377a88f9
2 years ago
3dc3978a10
Test navmodel ( #28272 )
...
* Test navmodel
* removed comment
* Updated model_replay ref
* read tiles from azure bucket
* updated ref commit
old-commit-hash: 2d34083cd8
2 years ago
a4af0fca74
jenkins fixups
...
old-commit-hash: 5f66a9a621
2 years ago
b3626c8ecd
model_replay: use last N frames of segment so navRoute is valid ( #26790 )
...
* model_replay: use last N frames of segment so navRoute is valid
* Use llk logMonoTime for MapRenderState.locationMonoTime
* Record mapRenderState
* update refs
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: 5ab2fc16ab
2 years ago
44098cc024
navmodel: check images in replay test ( #26747 )
...
* move position
* log images
* enable test
* update refs
* ignore
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: f3a711953a
2 years ago
01db07375c
nav model replay ( #26697 )
...
* nav model replay
* set token
* fix gh actions
* update refs
* fix pc
old-commit-hash: 1da6f6a6e2
2 years ago
7dac75758d
model replay speedup ( #26181 )
...
* model replay speedup
* less frames too
Co-authored-by: Comma Device <device@comma.ai>
old-commit-hash: 188c2c1c5e
3 years ago
a8ec6f4cfd
Rocket Launcher Model ( #25963 )
...
* 1456d261-d232-4654-8885-4d9fde883894/440 6b7d7cec-ead8-40f3-86cc-86d52c9b03fe/300
* compute only 9 tokens: 1456d261-d232-4654-8885-4d9fde883894/440 6b7d7cec-ead8-40f3-86cc-86d52c9b03fe/300
* tinygrad: cleanup gather
* 1456d261-d232-4654-8885-4d9fde883894/440 6b7d7cec-ead8-40f3-86cc-86d52c9b03fe/700
* empty commit for tests
* bump tinygrad
* dont use tinygrad matmul for now
* bump tinygrad
* 1456d261-d232-4654-8885-4d9fde883894/440 e63ab895-2222-4abd-a9a5-af86bb70e260/700
* float16 1456d261-d232-4654-8885-4d9fde883894/440 e63ab895-2222-4abd-a9a5-af86bb70e260/700
* increase steer rate cost
* Revert "increase steer rate cost"
This reverts commit 74ce9ab9be7ef17ecfec931f96851b12f37f2336.
* fork tinygrad
* empty commit for tests
* basics
* Kinda works
* new lat
* new tuning
* Move LATMPCN so scons compiles
* Update long weights
* Add tinygrad optim
* Update model ref
* update weights
* Update ref
* Try
* Error message for field ignore
* update model regf
* ref commit
* Fix onnx test
Co-authored-by: Yassine Yousfi <yyousfi1@binghamton.edu>
old-commit-hash: cb0b7375b7
3 years ago
35ff65121e
pre-commit: add codespell ( #25571 )
...
old-commit-hash: 6590fb2b93
3 years ago
64195b3c99
process replay: print correct ref path ( #25448 )
...
* fix log paths ref printing in process replay
* rm that
* this is easier to read
* fix model_replay
old-commit-hash: 4602e5a8f9
3 years ago
48522500ea
Falcon Punch Model: turn cutting improvements ( #25413 )
...
* simplified change to mpc dynamics
* add jerk pts
* increase jerk cost
* increase jerk pts multipler to master value
* Add final commit
* 1456d261-d232-4654-8885-4d9fde883894/440 ac1a6744-85b0-4ec6-8ba7-608d0717b8f1/750
* some copies are useful
* update model replay ref
* less frames in model replay onnx cpu
* 1456d261-d232-4654-8885-4d9fde883894/440 264b67f5-3f52-4b58-b11f-58dd8aaf08bf/950
* 1456d261-d232-4654-8885-4d9fde883894/440 236fc556-fba3-4255-8ccf-684b22637160/950
* c9d10c64-bea4-41ec-8ca3-d8c886fda172/440 26d73dd2-862a-44ae-bbdd-32cc4f397ad7/900
* Fix couple tests
* Update ref
* Unused for now
* Add lateral factor comment
* Unused variable
Co-authored-by: nuwandavek <vivekaithal44@gmail.com>
Co-authored-by: Bruce Wayne <yassine@comma.ai>
Co-authored-by: Yassine Yousfi <yyousfi1@binghamton.edu>
Co-authored-by: Bruce Wayne <batman@gpu06.internal>
old-commit-hash: 041458f632
3 years ago
6709805020
Model file too big: Revert "New model: minor fixes" ( #25390 )
...
Revert "New model: minor fixes (#25368 )"
This reverts commit 4e69dfab07507510eb52f532e7038b01f83471b7.
old-commit-hash: 3afe7464df
3 years ago
f8a05617a3
New model: minor fixes ( #25368 )
...
* 1456d261-d232-4654-8885-4d9fde883894/440 ac1a6744-85b0-4ec6-8ba7-608d0717b8f1/750
* some copies are useful
* update model replay ref
* less frames in model replay onnx cpu
Co-authored-by: Bruce Wayne <yassine@comma.ai>
Co-authored-by: Yassine Yousfi <yyousfi1@binghamton.edu>
old-commit-hash: 55bf938504
3 years ago
e5589e572f
Cleanup calibration code ( #25119 )
...
* First attempt
* worksish
* tests pass
* cleanup
* get rid of garbahe
* fix name
* Still used in xx
* add debug functions
* used
* Revert "used"
This reverts commit 276e8ebab06d2d4f0e9927ba32b7d8aca2bf88c3.
* Update ref
old-commit-hash: 772b748689
3 years ago
e53cd5ac1f
model_replay: update format_diff call
...
old-commit-hash: ef00bf76c1
3 years ago
ZwX1616
Maxime Desroches
YassineYousfi
Harald Schäfer
Shane Smiskol
Kacper Rączy
Adeeb Shihadeh
Justin Newberry
Mitchell Goff